Artificial Intelligence in Pharmaceutical Sciences

Artificial Intelligence-Assisted Optimization of Antipigmentation Tyrosinase Inhibitors: De Novo Molecular Generation Based on a Low Activity Lead Compound

“…The melting points were measured on an X-4BII+ microscope melting point apparatus. 1 H NMR and 13 C NMR spectra were recorded on Bruker instruments at frequencies of 500 and 125 MHz, respectively, with tetramethylsilane serving as an internal standard. High-resolution mass spectra were obtained using an Agilent 1290LC-6530QTOF instrument, with electron spray ionization used as the ion source.…”

“…For the in vivo toxicity test, 15 zebrafish were randomly selected and treated in 6-well plates. All compounds (kojic acid, T0, and T3) were dissolved in fish water at different concentrations (1,2,5,10,20, and 50 μM) for 3 mL/well. After the zebrafish were incubated at 28 °C for 45 h in the dark, 8 fish from each group were randomly selected for analysis under an anatomical microscope.…”

“…The development and progress of machine learning (ML) and deep learning (DL) technologies in the field of artificial intelligence (AI) have brought revolutionary changes to drug discovery . These technologies demonstrate immense potential in various stages of drug discovery and development, including target identification, de novo molecule design, drug screening, chemical synthesis, multipharmacology, drug repurposing, preclinical research, approval, and postmarket analysis. − They have made significant contributions to enhancing efficiency, reducing costs, and accelerating the discovery of novel drugs. In the case of target validation, de novo drug molecular design and generation, in particular, hold promise as pivotal starting points in drug discovery .…”

Continuous flow synthesis enabling reaction discovery

“…On the other hand, the data field available to AI/ML for synthesis currently is very limited and not yet standardised and slows progress in the area. Nevertheless, there are obvious areas where AI/ML impacts, for example in synthesis route design, 84 optimisation, 84 a – d scale-up 85 and automation. 84 e ,85 More innovation, however, will likely arise through their application in new high-throughput reaction discovery platforms, self-optimisation protocols and function linked synthesis.…”

“…Nevertheless, there are obvious areas where AI/ML impacts, for example in synthesis route design, 84 optimisation, 84 a – d scale-up 85 and automation. 84 e ,85 More innovation, however, will likely arise through their application in new high-throughput reaction discovery platforms, self-optimisation protocols and function linked synthesis. The serendipitous nature of new reaction discovery and the disconnected leaps of faith common to innovative chemical progress provide a very challenging but exciting environment for the future incorporation of AI.…”